Search results for: training curriculum

Authors: Dongkwon Han, Sangho Kim, Sunil Kwon

Abstract:

Unconventional gas resources have dramatically changed the future energy landscape. Unlike conventional gas resources, the key challenges in unconventional gas have been the requirement that applies to advanced approaches for production forecasting due to uncertainty and complexity of fluid flow. In this study, artificial neural network (ANN) model which integrates machine learning and data-driven approach was developed to predict productivity in shale gas. The database of 129 wells of Eagle Ford shale basin used for testing and training of the ANN model. The Input data related to hydraulic fracturing, well completion and productivity of shale gas were selected and the output data is a cumulative production. The performance of the ANN using all data sets, clustering and variables importance (VI) models were compared in the mean absolute percentage error (MAPE). ANN model using all data sets, clustering, and VI were obtained as 44.22%, 10.08% (cluster 1), 5.26% (cluster 2), 6.35%(cluster 3), and 32.23% (ANN VI), 23.19% (SVM VI), respectively. The results showed that the pre-trained ANN model provides more accurate results than the ANN model using all data sets.

Keywords: unconventional gas, artificial neural network, machine learning, clustering, variables importance

Procedia PDF Downloads 179

Authors: Yixiu Liu, Yunzhou Zhang, Jianning Chi, Hao Chu, Rui Zheng, Libo Sun, Guanghao Chen, Fangtong Zhou

Abstract:

In the last few years, large-scale person re-identification has attracted a lot of attention from video surveillance since it has a potential application prospect in public safety management. However, it is still a challenging job considering the variation in human pose, the changing illumination conditions and the lack of paired samples. Although the accuracy has been significantly improved, the data dependence of the sample training is serious. To tackle this problem, a new strategy is proposed based on bag of visual words (BoVW) model of designing the feature representation which has been widely used in the field of image retrieval. The local features are extracted, and more discriminative feature representation is obtained by cross-view dictionary learning (CDL), then the assignment map is obtained through k-means clustering. Finally, the BoVW histograms are formed which encodes the images with the statistics of the feature classes in the assignment map. Experiments conducted on the CUHK03, Market1501 and MARS datasets show that the proposed method performs favorably against existing approaches.

Keywords: bag of visual words, cross-view dictionary learning, person re-identification, reranking

Procedia PDF Downloads 178

Authors: Suleiman Musa, Shuaibu Sidi Safiyanu

Abstract:

This study examined the digital preservation in Nigeria university libraries. A comparison between the university of Nigeria Nsukka (UNN) and Ahmadu Bello University Zaria (ABU, Zaria). The study utilized primary source of data obtained from two selected institution librarians. Finding revealed varying results in terms of skills acquired by librarians before and after digitization of the two institutions. The study reports that journals publication, text book, CD-ROMS, conference papers and proceedings, theses, dissertations and seminar papers are among the information resources available for digitization. The study further documents that copyright issue, power failure, and unavailability of needed materials are among the challenges facing the digitization of library of the institution. On the basis of the finding, the study concluded that digitization of library enhances efficiency in organization and retrieval of information services. The study therefore recommended that software should be upgraded with backup, training of the librarians on digital process, installation of antivirus and enhancement of technical collaboration between the library and MIS.

Keywords: digitalization, preservation, libraries, comparison

Procedia PDF Downloads 313

Authors: Bayu Anggara, Arita Dewi Nugrahini, Didik Purwadi

Abstract:

Dry sorting workstation needs labor to produce green tea in Gambung Tea Factory. Observation results show that there is labor who are not working at the moment and doing overtime jobs to meet production targets. The measurement of the level of labor effectiveness has never been done before. The purpose of this study is to determine the level of labor effectiveness and provide recommendations for improvement based on the results of the Pareto diagram and Ishikawa diagram. The method used to measure the level of labor effectiveness is Overall Labor Effectiveness (OLE). OLE had three indicators which are availability, performance, and quality. Recommendations are made based on the results of the Pareto diagram and Ishikawa diagram for indicators that do not meet world standards. Based on the results of the study, the OLE value was 68.19%. Recommendations given to improve labor performance are adding mechanics, rescheduling rest periods, providing special training for labor, and giving rewards to labor. Furthermore, the recommendations for improving the quality of labor are procuring water content measuring devices, create material standard policies, and rescheduling rest periods.

Keywords: Ishikawa diagram, labor effectiveness, OLE, Pareto diagram

Procedia PDF Downloads 208

Authors: J. K. Adedeji, M. O. Oyekanmi

Abstract:

This paper has critically examined the use of Machine Learning procedures in curbing unauthorized access into valuable areas of an organization. The use of passwords, pin codes, user’s identification in recent times has been partially successful in curbing crimes involving identities, hence the need for the design of a system which incorporates biometric characteristics such as DNA and pattern recognition of variations in facial expressions. The facial model used is the OpenCV library which is based on the use of certain physiological features, the Raspberry Pi 3 module is used to compile the OpenCV library, which extracts and stores the detected faces into the datasets directory through the use of camera. The model is trained with 50 epoch run in the database and recognized by the Local Binary Pattern Histogram (LBPH) recognizer contained in the OpenCV. The training algorithm used by the neural network is back propagation coded using python algorithmic language with 200 epoch runs to identify specific resemblance in the exclusive OR (XOR) output neurons. The research however confirmed that physiological parameters are better effective measures to curb crimes relating to identities.

Keywords: biometric characters, facial recognition, neural network, OpenCV

Procedia PDF Downloads 239

Authors: Amanda Burrell, Tonia Gary, David Wright, Kumara Ward

Abstract:

This paper explores the concept of academic identity as it relates to the lecture, in particular, the digitized lecture delivered to a camera, in the absence of a student audience. Many academics have the performance aspect of the role thrust upon them with little or no training. For the purpose of this study, we look at the performance of the academic identity and examine tailored film presence coaching for its contributions toward academic identity, specifically in relation to feelings of self-confidence and diminishment of discomfort or stage fright. The case is articulated through the lens of scholar-practitioners, using expert facilitated participatory action research. It demonstrates in our sample of experienced academics, all reported some feelings of uncertainty about presenting lectures to camera prior to coaching. We share how power poses and reframing fear, produced improvements in the ease and competency of all participants. We share exactly how this insight could be adapted for self-coaching by any academic when called to present to a camera and consider the relationship between this and academic identity.

Keywords: academic identity, digitized lecture, embodied learning, performance coaching

Procedia PDF Downloads 323

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 163

Authors: Nevine Henry Wasef

Abstract:

The research discusses how Egyptian citizens perceive the performance of public sector officials, particularly the ethical values manifested in their behavior. It aims at answering the question of how Egyptian citizens’ perception of public officials affects citizens' trust in the government at large and the process of public service delivery specifically. The hypothesis is that public opinion about civil servants’ ethical values would be proportional to citizens’ trust in the government, which means that the more citizens regard administrators with high ethical standards, the higher trust in the government they would have and vice versa. The research would focus on the independent variable of trust in the government and the dependent variable of public perception of administrators’ ethical performance. The data would be collected through surveys designed to measure the public evaluation of public officials they are interacting with and the quality of services delivered to them. The study concludes that implementing ethical values in public administration has a crucial role in improving citizens’ trust in the government based on various case studies of governments that successfully adopted ethical training programs for their civil servants.

Keywords: trust, distrust, ethics, performance, integrity, values, public service

Procedia PDF Downloads 73

Authors: Firas M. Tuaimah, Huda M. Abdul Abbas

Abstract:

Accurate Short Term Load Forecasting (STLF) is essential for a variety of decision making processes. However, forecasting accuracy can drop due to the presence of uncertainty in the operation of energy systems or unexpected behavior of exogenous variables. Interval Type 2 Fuzzy Logic System (IT2 FLS), with additional degrees of freedom, gives an excellent tool for handling uncertainties and it improved the prediction accuracy. The training data used in this study covers the period from January 1, 2012 to February 1, 2012 for winter season and the period from July 1, 2012 to August 1, 2012 for summer season. The actual load forecasting period starts from January 22, till 28, 2012 for winter model and from July 22 till 28, 2012 for summer model. The real data for Iraqi power system which belongs to the Ministry of Electricity.

Keywords: short term load forecasting, prediction interval, type 2 fuzzy logic systems, electric, computer systems engineering

Procedia PDF Downloads 381

Authors: Freda E. Asem, R. D. Osei, D. B. Sarpong, J. K. Kuwornu

Abstract:

While market access remains important, Ghana’s major handicap is her inability to sustain export growth on the open market. The causes of these could be attributed to inefficiency, lack of competitiveness and supply-side constraints. This study examined the challenges faced by smallholder horticultural farmers and how it relates to their technical efficiency. The study employed mixed methods to address the problem. Using the Millennium Development Account (MiDA) Farmer Based Organization survey data on farm households in 23 districts in Ghana, the study assessed the technical efficiency of smallholder horticultural farmers (taking into account production risks). Focus group discussions (FGDs) and in-depth interviews were also conducted on smallholder mango, pineapple, and chilli pepper farmers selected districts in Ghana. Results revealed the constraints faced by smallholder horticultural farmers to be marketing, training, funding, accessibility, and affordability of inputs, land, access to credit, and the disconnect between themselves and policy makers and implementers.

Keywords: productivity, gender, policy, efficiency, constraints

Procedia PDF Downloads 468

Authors: Atuhurra Jesse, N'guessan Yves-Roland Douha, Pabitra Lenka

Abstract:

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, image classifiers to detect CSSVD-infected cacao plants are presented in this study. The classifiers are based on VGG16, ResNet50 and Vision Transformer (ViT). The image classifiers are evaluated on a recently released and publicly accessible KaraAgroAI Cocoa dataset. The best performing image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. These results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.

Keywords: CSSVD, image classification, ResNet50, vision transformer, KaraAgroAI cocoa dataset

Procedia PDF Downloads 81

Authors: A. van Staden, M. M. Coetzee

Abstract:

Despite numerous efforts to increase the literacy level of South African learners, for example, through the implementation of educational policies such as the Revised National Curriculum statement, advocating mother-tongue instruction (during a child's formative years), in reality, the majority of South African children are still being educated in a second language (in most cases English). Moreover, despite the fact that a significant percentage of our country's budget is spent on the education sector and that both policy makers and educationalists have emphasized the importance of learning English in this globalized world, the poor overall academic performance and English literacy level of a large number of school leavers are still a major concern. As we move forward in an attempt to comprehend the nuances of English language and literacy development in our country, it is imperative to explore both extrinsic and intrinsic factors that contribute or impede the effective development of English as a second language. In the present study, the researchers set out to investigate how intrinsic factors such as motivation and self-concept contribute to or affect English language learning amongst high school learners in South Africa. Emanating from the above the main research question that guided this research is the following: Is there a significant relationship between high school learners' self-concept, motivation, and English second language performances? In order to investigate this hypothesis, this study utilized quantitative research methodology to investigate the interplay of self-concept and motivation in English language learning. For this purpose, we sampled 201 high school learners from various schools in South Africa. Methods of data gathering inter alia included the following: A biographical questionnaire; the Academic Motivational Scale and the Piers-Harris Self-Concept Scale. Pearson Product Moment Correlation Analyses yielded significant correlations between L2 learners' motivation and their English language proficiency, including demonstrating positive correlations between L2 learners' self-concept and their achievements in English. Accordingly, researchers have argued that the learning context, in which students learn English as a second language, has a crucial influence on students' motivational levels. This emphasizes the important role the teacher has to play in creating learning environments that will enhance L2 learners' motivation and improve their self-concepts.

Keywords: motivation, self-concept, language learning, English second language learners (L2)

Procedia PDF Downloads 249

Authors: Piyawan Srisuruk, Janya Boonmeeprasert, Romwarin Gamlunglert, Benjamaporn Choikhruea, Ornjira Jaraepram, Jarin Boonsuchat, Sakdadech Singkibud, Kusalaporn Chaiudomsom, Chanatiporn Chonprai, Pornchanaka Tana, Suchat Paholpak

Abstract:

Objective: To develop an Intensive and comprehensive program (ICP) for the Inclusive Class Teacher (ICPICT) to teach elementary students (ES) with ASD in order to enhance the students’ academic and social skills (ASS) and to study the effect of the teaching program. Methods: The purposive sample included 15 Khon Kaen inclusive class teachers and their 15 elementary students. All the students were diagnosed by a child and adolescent psychiatrist to have DSM-5 level 1 ASD. The study tools included 1) an ICP to teach teachers about ASD, a teaching method to enhance academic and social skills for ES with ASD, and an assessment tool to assess the teacher’s knowledge before and after the ICP. 2) an ICPICT to teach ES with ASD to enhance their ASS. The project taught 10 sessions, 3 hours each. The ICPICT had its teaching structure. Teaching media included: pictures, storytelling, songs, and plays. The authors taught and demonstrated to the participant teachers how to teach with the ICPICT until the participants could display the correct teaching method. Then the teachers taught ICPICT at school by themselves 3) an assessment tool to assess the students’ ASS before and after the completion of the study. The ICP to teach the teachers, the ICPICT, and the relevant assessment tools were developed by the authors and were adjusted until consensus agreed as appropriate for researching by 3 curriculum of teaching children with ASD experts. The data were analyzed by descriptive and analytic statistics via SPSS version 26. Results: After the briefing, the teachers increased the mean score, though not with statistical significance, of knowledge of ASD and how to teach ES with ASD on ASS (p = 0.13). Teaching ES with ASD with the ICPICT could increase the mean scores of the students’ skills in learning and expressing social emotions, relationships with a friend, transitioning, and skills in academic function 3.33, 2.27, 2.94, and 3.00 scores (full scores were 18, 12, 15 and 12, Paired T-Test p = 0.007, 0.013, 0.028 and 0.003 respectively). Conclusion: The program to teach academic and social skills simultaneously in an intensive and comprehensive structure could enhance both the academic and social skills of elementary students with ASD. Keywords: Elementary students, autism spectrum, academic skill, social skills, intensive program, comprehensive program, integration.

Keywords: academica and social skills, students with autism, intensive and comprehensive, teaching program

Procedia PDF Downloads 53

Authors: Temitope Adewale, Oladapo Raji

Abstract:

The study was designed to investigate the assessment of women's involvement in fishing. In order to give the study a direction, five research questions, as well as two hypotheses, were postulated, and a total of fifty (50) respondents each were selected from two local government areas for the study. This brings a total of one hundred (100) respondents selected from these local government areas in Lagos state. The outcome of the finding indicates that the percentage of the respondents’ age, 49% was between 31 and 35 years, 56% has a working experience of 6-10 years, 61% were married, 69% had secondary education as their educational level. However, findings show that socio-economic characteristics (x2 =15.504, df=6, p < 0.05) and income (r=0.83, p < 0.05) have a significant relationship on the fishing. It was established that the Women in Fish production/processing were faced with a lot of constraints such as high cost of inputs, inadequate electricity supply, lack of adequate capital, non-availability of the improved oven, non-availability of extension agents, inadequate fish landing, lack of transportation facilities, lack of training on financial management and loan acquisition which affected the level of output of women in Fish processing adversely.

Keywords: women, fishing, agriculture, Lagos

Procedia PDF Downloads 120

Authors: Olga Castiblanco, Diego Vizcaíno

Abstract:

Changing the traditional way of using experimentation in science teaching is quite a challenge. This research results talk about the characterization of physics experiments, not because of the topic it deals with, nor depending on the material used in the assemblies, but related to the possibilities it offers to enrich interaction in the classroom and thereby contribute to the development of scientific thinking skills. It is an action-research of type intervention in the classroom, with four courses of Physics Teaching undergraduate students from a public university in Bogotá. This process allows characterizing typologies such as discrepant, homemade, illustrative, research, recreational, crucial, mental, and virtual experiments. Students' production and researchers' reports on each class were the most relevant data. Content analysis techniques let to categorize the information and obtain results on the richness that each typology of experiment offers when interacting in the classroom. Results show changes in the comprehension of new teachers' role, far from being the possessor and transmitter of the truth. Besides, they understand strategies to engage students effectively since the class advances extending ideas, reflections, debates, and questions, either towards themselves, their classmates, or the teacher.

Keywords: physics teacher training, non-traditional experimentation, contextualized education, didactics of physics

Procedia PDF Downloads 77

Authors: Jill Steel

Abstract:

The interlinked issues of emotional wellbeing and attainment continue to dominate international educational discourse. Reading skills are particularly important to attainment in all areas of the curriculum, and illiteracy is associated with reduced wellbeing and life prospects, with serious ramifications for the wider economy and society. Research shows that reading attainment is influenced by reading motivation and frequency. Reading to Dogs (RTD) is increasingly applied to promote reading motivation and frequency in schools despite a paucity of empirical evidence, specifically examining the influence of RTD on emotional wellbeing and engagement with reading. This research aims to examine whether RTD is effective in promoting these positive outcomes among children aged eight to nine years. This study also aims to inform much needed regulation of the field and standards of practice, including both child and dog welfare. Therefore, ethical matters such as children’s inclusion and safety, as well as the rights and wellbeing of dogs infuse the study throughout. The methodological design is a mixed method longitudinal study. A UK wide questionnaire will be distributed to teachers between January and June 2020 to understand their perceptions of RTD. Following this, a randomised controlled trial (N = 100) will begin in August 2020 in two schools of a comparable demographic, with N= 50 in the intervention school, and N= 50 in a waiting list control school. Reading and wellbeing assessments will be conducted prior to and immediately post RTD, and four weeks after RTD to measure sustained changes. The reading assessments include New Group Reading Test, Motivation to Read Profile (Gambrell et al., 1995), as well as reading frequency and reading anxiety assessments specifically designed for the study. Wellbeing assessments include Goodman’s SDQ, (1997) and pupil self-reporting questionnaires specifically designed for the study. Child, class teacher, and parent questionnaires and interviews prior to, during and post RTD will be conducted to measure perceptions of the impact of RTD on mood and motivation towards reading. This study will make a substantial contribution to our understanding of the effectiveness of RTD and thus have consequences for the fields of education and anthrozoology.

Keywords: animal assisted intervention, reading to dogs, welfare, wellbeing

Procedia PDF Downloads 152

Authors: Neerav Kumar, Naumaan Nayyar, Sharath Kashyap

Abstract:

Most companies see an increase in the adoption of machine learning (ML) applications across internal and external-facing use cases. ML applications vend output either in batch or real-time patterns. A complete batch ML pipeline architecture comprises data sourcing, feature engineering, model training, model deployment, model output vending into a data store for downstream application. Due to unclear role expectations, we have observed that scientists specializing in building and optimizing models are investing significant efforts into building the other components of the architecture, which we do not believe is the best use of scientists’ bandwidth. We propose a system architecture created using AWS services that bring industry best practices to managing the workflow and simplifies the process of model deployment and end-to-end data integration for an ML application. This narrows down the scope of scientists’ work to model building and refinement while specialized data engineers take over the deployment, pipeline orchestration, data quality, data permission system, etc. The pipeline infrastructure is built and deployed as code (using terraform, cdk, cloudformation, etc.) which makes it easy to replicate and/or extend the architecture to other models that are used in an organization.

Keywords: data pipeline, machine learning, AWS, architecture, batch machine learning

Procedia PDF Downloads 47

Authors: Nilanthi Ratnayake, Wen-Ling Liu

Abstract:

Prior research indicates an increasing gap between the skills and capabilities of graduates in the contemporary workplace across the globe. The challenge of addressing this issue primarily lies on the hands of higher education institutes/universities. In particular, surveys of UK employers and retailers found that soft skills including communication, numeracy, teamwork, confidence, analytical ability, digital/IT skills, business sense, language, and social skills are highly valued by graduate employers, and in achieving this, there are various assessed and non-assessed learning exercises have already been embedded into the university curriculum. To this end, this research study aims to explore the reflections of postgraduate student participation in a live commercial project (i.e. designing an advertising campaign for open days, summer school etc.) implemented with the intention of offering a transformative experience by deploying this project. Qualitative research methodology has been followed in this study, collecting data from three types of target audiences; students, academics and employers via a series of personal interviews and focus group discussions. Recorded data were transcribed, entered into NVIVO, and analysed using meaning condensation and content analysis. Students reported that they had a very positive impact towards improving self-efficacy, especially in relation to soft skills and confidence in seeking employment opportunities. In addition, this project has reduced cultural barriers for international students in general communications. Academic staff and potential employers who attended on the presentation day expressed their gratitude for offering a lifelong experience for students, and indeed believed that these type of projects contribute significantly to enhance skills and capabilities of students to cater the demands of employers. In essence, key findings demonstrate that an integration of knowledge-based skills into a live commercial project facilitate individuals to make the transition from education to employment in terms of skills, abilities and work behaviours more effectively in comparison to some other activities/assuagements that are currently in place in higher education institutions/universities.

Keywords: soft skills, commercially live project, higher education, student participation

Procedia PDF Downloads 343

Authors: Ninlawat Phuangchoke, Waraporn Viyanon, Setta Sasananan

Abstract:

The most important process of the water treatment plant process is the coagulation using alum and poly aluminum chloride (PACL), and the value of usage per day is a hundred thousand baht. Therefore, determining the dosage of alum and PACL are the most important factors to be prescribed. Water production is economical and valuable. This research applies an artificial neural network (ANN), which uses the Levenberg–Marquardt algorithm to create a mathematical model (Soft Jar Test) for prediction chemical dose used to coagulation such as alum and PACL, which input data consists of turbidity, pH, alkalinity, conductivity, and, oxygen consumption (OC) of Bangkhen water treatment plant (BKWTP) Metropolitan Waterworks Authority. The data collected from 1 January 2019 to 31 December 2019 cover changing seasons of Thailand. The input data of ANN is divided into three groups training set, test set, and validation set, which the best model performance with a coefficient of determination and mean absolute error of alum are 0.73, 3.18, and PACL is 0.59, 3.21 respectively.

Keywords: soft jar test, jar test, water treatment plant process, artificial neural network

Procedia PDF Downloads 151

Authors: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 128

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 242

Authors: Jaspreet Singh, Gurvinder Singh, Prabhsimran Singh, Rajinder Singh, Prithvipal Singh, Karanjeet Singh Kahlon, Ravinder Singh Sawhney

Abstract:

Morphological evaluation of Indian languages is one of the burgeoning fields in the area of Natural Language Processing (NLP). The evaluation of a language is an eminent task in the era of information retrieval and text mining. The extraction and classification of knowledge from text can be exploited for sentiment analysis and morphological evaluation. This study coalesce morphological evaluation and sentiment analysis for the task of classification of farmer suicide cases reported in Punjab state of India. The pre-processing of Punjabi text involves morphological evaluation and normalization of Punjabi word tokens followed by the training of proposed model using deep learning classification on Punjabi language text extracted from online Punjabi news reports. The class-wise accuracies of sentiment prediction for four negatively oriented classes of farmer suicide cases are 93.85%, 88.53%, 83.3%, and 95.45% respectively. The overall accuracy of sentiment classification obtained using proposed framework on 275 Punjabi text documents is found to be 90.29%.

Keywords: deep neural network, farmer suicides, morphological processing, punjabi text, sentiment analysis

Procedia PDF Downloads 303

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 227

Authors: Kaoutar Ben Azzou, Hanaa Talei

Abstract:

Human resources is an important department in each organization as it manages the life cycle of employees from recruitment training to retirement or termination of contracts. The recruitment process starts with a job opening, followed by a selection of the best-fit candidates from all applicants. Matching the best profile for a job position requires a manual way of looking at many CVs, which requires hours of work that can sometimes lead to choosing not the best profile. The work presented in this paper aims at reducing the workload of HR personnel by automating the preliminary stages of the candidate screening process, thereby fostering a more streamlined recruitment workflow. This tool introduces an automated system designed to help with the recruitment process by scanning candidates' CVs, extracting pertinent features, and employing machine learning algorithms to decide the most fitting job profile for each candidate. Our work employs natural language processing (NLP) techniques to identify and extract key features from unstructured text extracted from a CV, such as education, work experience, and skills. Subsequently, the system utilizes these features to match candidates with job profiles, leveraging the power of classification algorithms.

Keywords: automated recruitment, candidate screening, machine learning, human resources management

Procedia PDF Downloads 37

Authors: Widyani Fatwa Dewi, Subroto Athor

Abstract:

In a telecommunication service provider, quantity and interval of customer demand often difficult to predict due to high dependency on customer expansion strategy and technological development. Demand arrives when a customer needs to add capacity to an existing site or build a network in a new site. Because demand is uncertain for each period, and sometimes there is a null demand for several equipments, it is categorized as intermittent. This research aims to improve demand forecast quality in Indonesia's telecommunication service providers by using Artificial Neural Network. In Artificial Neural Network, the pattern or relationship within data will be analyzed using the training process, followed by the learning process as validation stage. Historical demand data for 36 periods is used to support this research. It is found that demand forecast by using Artificial Neural Network outperforms the existing method if it is reviewed on two criteria: the forecast accuracy, using Mean Absolute Deviation (MAD), Mean of the sum of the Squares of the Forecasting Error (MSE), Mean Error (ME) and service level which is shown through inventory cost. This research is expected to increase the reference for a telecommunication demand forecast, which is currently still limited.

Keywords: artificial neural network, demand forecast, forecast accuracy, intermittent, service level, telecommunication

Procedia PDF Downloads 148

Authors: Meruert Serik, Nassipzhan Duisegaliyeva, Danara Tleumagambetova

Abstract:

The article highlights and describes the characteristic features of real-time face detection in images and videos using machine learning algorithms. Students of educational programs reviewed the research work "6B01511-Computer Science", "7M01511-Computer Science", "7M01525- STEM Education," and "8D01511-Computer Science" of Eurasian National University named after L.N. Gumilyov. As a result, the advantages and disadvantages of Haar Cascade (Haar Cascade OpenCV), HoG SVM (Histogram of Oriented Gradients, Support Vector Machine), and MMOD CNN Dlib (Max-Margin Object Detection, convolutional neural network) detectors used for face detection were determined. Dlib is a general-purpose cross-platform software library written in the programming language C++. It includes detectors used for determining face detection. The Cascade OpenCV algorithm is efficient for fast face detection. The considered work forms the basis for the development of machine learning methods by future computer science teachers.

Keywords: algorithm, artificial intelligence, education, machine learning

Procedia PDF Downloads 60

Authors: Farhad Asadi, Mohammad Javad Mollakazemi, Aref Ghafouri

Abstract:

Recent research in neural networks science and neuroscience for modeling complex time series data and statistical learning has focused mostly on learning from high input space and signals. Local linear models are a strong choice for modeling local nonlinearity in data series. Locally weighted projection regression is a flexible and powerful algorithm for nonlinear approximation in high dimensional signal spaces. In this paper, different learning scenario of one and two dimensional data series with different distributions are investigated for simulation and further noise is inputted to data distribution for making different disordered distribution in time series data and for evaluation of algorithm in locality prediction of nonlinearity. Then, the performance of this algorithm is simulated and also when the distribution of data is high or when the number of data is less the sensitivity of this approach to data distribution and influence of important parameter of local validity in this algorithm with different data distribution is explained.

Keywords: local nonlinear estimation, LWPR algorithm, online training method, locally weighted projection regression method

Procedia PDF Downloads 486

Authors: Pornpimol Chaiwuttisak

Abstract:

The study aims to compare the performance of the logistics for Thailand’s wholesale and retail trade industries (except motor vehicles, motorcycle, and stalls) by using data (data envelopment analysis). Thailand Standard Industrial Classification in 2009 (TSIC - 2009) categories that industries into sub-group no. 45: wholesale and retail trade (except for the repair of motor vehicles and motorcycles), sub-group no. 46: wholesale trade (except motor vehicles and motorcycles), and sub-group no. 47: retail trade (except motor vehicles and motorcycles. Data used in the study is collected by the National Statistical Office, Thailand. The study consisted of four input factors include the number of companies, the number of personnel in logistics, the training cost in logistics, and outsourcing logistics management. Output factor includes the percentage of enterprises having inventory management. The results showed that the average relative efficiency of small-sized enterprises equals to 27.87 percent and 49.68 percent for the medium-sized enterprises.

Keywords: DEA, wholesales and retails, logistics, Thailand

Procedia PDF Downloads 403

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 129

Authors: Mamadou Diop, Florence Crick, Momadou Sow, Kate Elizabeth Gannon

Abstract:

Understanding SME leaders’ responses to climate is essential to cope with ongoing changes in temperature and rainfall. This study analyzes the response of SME leaders to the adverse effects of climate change in semi-arid lands (SAL) in Senegal. Based on surveys administrated to 161 SME leaders, this research shows that 91% of economic units are affected by climatic conditions, although 70% do not have a plan to deal with climate risks. Economic actors have striven to take measures to adapt. However, their efforts are limited by various obstacles accentuated by a lack of support from public authorities. In doing so, substantial political, institutional and financial efforts at national and local levels are needed to promote an enabling environment for economic actors to adapt. This will focus on information and training about the threats and opportunities related to global warming, the creation of an adaptation support fund to support local initiatives and the improvement of the institutional, regulatory and political framework.

Keywords: small and medium-sized enterprises, climate change, adaptation, semi-arid lands

Procedia PDF Downloads 192